提示粒子物理：面向组合多任务的标记化多模态基础模型
Prompting Particle Physics: Tokenized Multi-modal Foundation Models for Combinatorially Many Tasks
浏览论文内容
中文总结 AI 辅助
本研究提出一种共享标记词汇的多模态基础模型，以单一网络统一对撞机实验中的粒子流、探测器模拟等多项重建与模拟任务，自回归模型在喷注重建指标上超越现有粒子流算法。
中文摘要 AI 辅助
对撞机实验中的重建和模拟是由一系列专门算法组成的长链条，每个算法仅针对单一步骤进行调优。我们探索一个模型如何同时服务于这些步骤中的多个环节，同时仍然生成中间对象（径迹、量热器单元、簇、粒子和喷注），使链条保持可解释性。为此，我们将喷注中的每个对象表示在一个共享的标记词汇表中，并训练一个模型将任意模态子集映射到任意其他子集。因此，一个任务仅在于选择提供哪些模态以及请求哪些模态：粒子流、探测器模拟和带电能量扣除都是通过同一组权重的不同方向。我们在所有模态组合上进行训练，解码器以自回归或并行方式发射标记。通过标记化，两种架构在少量调优下均能稳定训练。在评估中，两种模型均产生逼真的重建和模拟对象，其中自回归模型对Geant4输出的保真度尤为突出。自回归模型还在许多典型喷注重建指标上优于最先进的粒子流算法。
英文摘要
Reconstruction and simulation at a collider experiment are long chains of specialised algorithms, each tuned to a single step. We explore how one model can serve many of those steps at once, while still producing the intermediate objects (tracks, calorimeter cells, clusters, particles and jets) that make the chain interpretable. To do so, we represent every object in a jet in a single shared token vocabulary and train one model to map any subset of these modalities to any other. A task is then only a choice of which modalities to provide and which to request: particle flow, detector simulation and charged energy subtraction are all directions through the same set of weights. We train over all modality combinations, with a decoder emitting tokens either autoregressively or in parallel. With tokenisation, both architectures train stably with little tuning. In evaluations, both models produce realistic reconstruction and simulation objects, with the autoregressive model particularly faithful to output from Geant4. The autoregressive model also outperforms a state-of-the-art particle flow algorithm on many typical jet reconstruction metrics.
发表机构
- Technical University of Munich（慕尼黑工业大学）
机构由 AI 辅助整理，请以论文原文为准。
